Richard Sutton, the father of reinforcement learning, paper: pursuing a general model for intelligent decision makers

 The idea of this paper is to strengthen and deepen this premise by putting forward views on decision makers , This view in Psychology 、 Artificial intelligence 、 economics 、 Control theory and neuroscience have substantial and extensive applications , I call it a generic model for intelligent agents . The generic model does not include anything specific to any organism 、 Anything in the world or in the field of application . The generic model does include all aspects of the decision-maker's interaction with his world （ There must be input and output , And a goal ） And the internal components of the decision maker （ For perception 、 Decision making 、 Internal assessment and world model ）. I identified these aspects and components , Note that they are given different names in different disciplines , But essentially it means the same idea , The challenges and benefits of designing a neutral term that can be used across disciplines are discussed . It is time to recognize and establish the integration of multiple different disciplines on the substantive general model of intelligent agents .